Functional Connectivity Ensemble Method to Enhance BCI Performance (FUCONE)

Corsi, Marie‐Constance; Chevallier, Sylvain; Fallani, Fabrizio De Vico; Yger, Florian

doi:10.1109/tbme.2022.3154885

Cited by 10 publications

(6 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, our approach facilitates the integration of additional feature computation, as illustrated by the addition of pairwise phase-locking value matrices which we found to convey complementary information over the covariance for dementia diagnosis. At the methodological level, our work is related to recent non-deep Riemannian ensembling approaches in the BCI context which combined different types of EEG connectivity features –cast into SPD matrices– (Corsi et al, 2022) or stacked generalization (Wolpert, 1992) of sub-models for specific M/EEG features in the context of age prediction (Engemann et al, 2020; Sabbagh et al, 2023). Another recent study proposed a Bayesian method extending the tradition of ICA for unsupervised learning of oscillatory components, resembling our work in providing inference on relevant frequencies (Das et al, 2023).…”

Section: Discussionmentioning

confidence: 99%

GREEN: a lightweight architecture using learnable wavelets and Riemannian geometry for biomarker exploration

Paillard,

Hipp,

Engemann

2024

Preprint

View full text Add to dashboard Cite

Spectral analysis using wavelets has proven useful for analyzing electroencephalographic (EEG) signals and identifying biomarkers in a clinical context. Over the past decade, Riemannian geometry has crystalized as a theoretical framework providing robust methods for modeling biomedical outcomes and brain function from multi-channel EEG recordings. Combining both approaches yields applications with higher interpretability and efficiency. Yet these approaches rely on handcrafted rules and sequential optimization. On the contrary, the growing deep learning (DL) literature provides end-to-end trainable models for processing raw EEG. Despite state-of- the-art performance on various prediction tasks, clinical impact remains a challenge, which is at least in part due to their lack of interpretability and interoperability with established neuroscience concepts. In this work we introduce a new lightweight neural network for processing raw EEG data building on wavelet transforms and Riemannian geometry. The proposed architecture termed GREEN (Gabor Riemann EEGNet) is benchmarked on five different prediction tasks (age, sex, eyes-closed detection, dementia diagnosis, EEG pathology) from three different datasets (TUAB, CAUEEG, TDBRAIN) encompassing data from more than 5000 human participants. This new architecture significantly outperformed state-of-the-art non-deep models on several of the benchmarks and performed favorably compared to large DL models on the CAU bench- mark using orders of magnitude fewer parameters. Computational experiments revealed how GREEN facilitates learning sparse representations without compromising performance. We further demonstrate that the modularity of the GREEN architecture allows computing classical measures of phase synchrony, such as pairwise phase-locking values which are found to convey information relevant for predicting dementia diagnosis. Furthermore, the learned wavelets can easily be interpreted as bandpass filters, therefore making this architecture explainable by de- sign. We illustrate this with a classical example of the Berger effect i.e. modulation of 8-10Hz power when closing the eyes. By integrating domain-knowledge in architecture choices, the pro- posed model benefits from desirable complexity-performance trade-off and learns interpretable representations of EEG. The source code is made publicly available.

show abstract

Section: Discussionmentioning

confidence: 99%

GREEN: a lightweight architecture using learnable wavelets and Riemannian geometry for biomarker exploration

Paillard,

Hipp,

Engemann

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In the future, a thorough comparison with more methods and on more open datasets via MOABB 34 need to be done to further validate the utility of path signature for BCI applications. Ensemble learning could be employed to combine the covariance-based features and the signature-based features to further boost classification accuracy, as it has been shown to be effective with functional connectivity 35 . Besides, some general techniques to improve the performance of the signature method 36 , such as the lead-lag augmentation of the times series, could be attempted.…”

Section: Discussionmentioning

confidence: 99%

Signature methods for brain-computer interfaces

Xu,

Lee,

Drougard

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Brain-computer interfaces (BCIs) allow direct communication between one’s central nervous system and a computer without any muscle movement hence by-passing the peripheral nervous system. They can restore disabled people’s ability to interact with their environment, e.g. communication and wheelchair control. However, to this day their performance is still hindered by the non-stationarity of electroencephalography (EEG) signals, as well as their susceptibility to noise from the users’ environment and from their own physiological activity. Moreover, a non-negligible amount of users struggle to use BCI systems based on motor imagery. In this paper, a new method based on the path signature is introduced to tackle this problem by using features which are different from the usual power-based ones. The path signature is a series of iterated integrals computed from a multidimensional path. It is invariant under translation and time reparametrization, which makes it a robust feature for multichannel EEG time series. The performance can be further boosted by combining the path signature with the gold standard Riemannian classifier in the BCI field exploiting the geometric structure of symmetric positive definite (SPD) matrices. The results obtained on publicly available datasets show that the signature method is more robust to inter-user variability than classical ones, especially on noisy and low-quality data. Hence, this study paves the way towards the use of mathematical tools that until now have been neglected, in order to tackle the EEG-based BCI variability issue. It also sheds light on the lead-lag relationship captured by path signature which seems relevant to assess the underlying neural mechanisms.

show abstract

“…In addition, soft voting-based ensembles are effective in compensating for the weaknesses of individual classifiers and can achieve even better performance when combining classifiers trained on different features. The increased diversity in feature space is the key factor behind the performance improvement of ensemble classifiers, as it enhances their robustness to both inter- and intra-subject variability (Corsi et al, 2022 ). Due to the fact that C T and C S were trained on distinct datasets, namely x T and x S , respectively, their feature spaces are different and complementary.…”

Section: Methodsmentioning

confidence: 99%

Bridging the BCI illiteracy gap: a subject-to-subject semantic style transfer for EEG-based motor imagery classification

Kim

Shin

Kam

2023

Front. Hum. Neurosci.

View full text Add to dashboard Cite

IntroductionBrain-computer interfaces (BCIs) facilitate direct interaction between the human brain and computers, enabling individuals to control external devices through cognitive processes. Despite its potential, the problem of BCI illiteracy remains one of the major challenges due to inter-subject EEG variability, which hinders many users from effectively utilizing BCI systems. In this study, we propose a subject-to-subject semantic style transfer network (SSSTN) at the feature-level to address the BCI illiteracy problem in electroencephalogram (EEG)-based motor imagery (MI) classification tasks.MethodsOur approach uses the continuous wavelet transform method to convert high-dimensional EEG data into images as input data. The SSSTN 1) trains a classifier for each subject, 2) transfers the distribution of class discrimination styles from the source subject (the best-performing subject for the classifier, i.e., BCI expert) to each subject of the target domain (the remaining subjects except the source subject, specifically BCI illiterates) through the proposed style loss, and applies a modified content loss to preserve the class-relevant semantic information of the target domain, and 3) finally merges the classifier predictions of both source and target subject using an ensemble technique.Results and discussionWe evaluate the proposed method on the BCI Competition IV-2a and IV-2b datasets and demonstrate improved classification performance over existing methods, especially for BCI illiterate users. The ablation experiments and t-SNE visualizations further highlight the effectiveness of the proposed method in achieving meaningful feature-level semantic style transfer.

show abstract

Functional Connectivity Ensemble Method to Enhance BCI Performance (FUCONE)

Cited by 10 publications

References 78 publications

GREEN: a lightweight architecture using learnable wavelets and Riemannian geometry for biomarker exploration

GREEN: a lightweight architecture using learnable wavelets and Riemannian geometry for biomarker exploration

Signature methods for brain-computer interfaces

Bridging the BCI illiteracy gap: a subject-to-subject semantic style transfer for EEG-based motor imagery classification

Contact Info

Product

Resources

About